Time Series Project (S&P 500 Stock Market case-study)¶

Data collection on AAPL, AMZN, GOOG, and MSFT¶

In [1]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
In [2]:
import glob
In [3]:
glob.glob(r'C:\DA_BA_material\individual_stocks_5yr/*csv')
Out[3]:
['C:\\DA_BA_material\\individual_stocks_5yr\\AAL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AAPL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AAP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ABBV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ABC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ABT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ACN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ADBE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ADI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ADM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ADP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ADSK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ADS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AEE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AEP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AES_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AET_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AFL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AGN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AIG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AIV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AIZ_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AJG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AKAM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ALB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ALGN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ALK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ALLE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ALL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ALXN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AMAT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AMD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AME_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AMGN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AMG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AMP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AMT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AMZN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ANDV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ANSS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ANTM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AON_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AOS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\APA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\APC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\APD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\APH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\APTV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ARE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ARNC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ATVI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AVB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AVGO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AVY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AWK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AXP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AYI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\AZO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\A_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BAC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BAX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BBT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BBY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BDX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BEN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BF.B_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BHF_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BHGE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BIIB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BLK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BLL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BMY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BRK.B_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BSX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BWA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\BXP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CAG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CAH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CAT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CBG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CBOE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CBS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CCI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CCL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CDNS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CELG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CERN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CFG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CF_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CHD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CHK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CHRW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CHTR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CINF_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CLX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CMA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CMCSA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CME_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CMG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CMI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CMS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CNC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CNP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\COF_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\COG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\COL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\COO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\COP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\COST_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\COTY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CPB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CRM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CSCO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CSRA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CSX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CTAS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CTL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CTSH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CTXS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CVS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CVX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\CXO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\C_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DAL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DFS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DGX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DHI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DHR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DISCA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DISCK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DISH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DIS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DLR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DLTR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DOV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DPS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DRE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DRI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DTE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DUK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DVA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DVN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DWDP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\DXC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\D_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EBAY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ECL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ED_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EFX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EIX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EMN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EMR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EOG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EQIX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EQR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EQT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ESRX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ESS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ES_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ETFC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ETN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ETR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EVHC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EXC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EXPD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EXPE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\EXR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FAST_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FBHS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FCX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FDX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FFIV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FISV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FIS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FITB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FLIR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FLR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FLS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FMC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FOXA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FOX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FRT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FTI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\FTV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\F_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GGP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GILD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GIS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GLW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GOOGL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GOOG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GPC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GPN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GPS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GRMN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\GWW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HAL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HAS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HBAN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HBI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HCA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HCN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HCP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HES_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HIG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HII_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HLT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HOG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HOLX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HON_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HPE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HPQ_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HRB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HRL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HRS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HSIC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HST_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HSY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\HUM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IBM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ICE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IDXX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IFF_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ILMN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\INCY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\INFO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\INTC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\INTU_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IPG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IQV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IRM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ISRG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ITW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\IVZ_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\JBHT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\JCI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\JEC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\JNJ_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\JNPR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\JPM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\JWN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KEY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KHC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KIM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KLAC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KMB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KMI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KMX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KORS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KSS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\KSU_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\K_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LEG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LEN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LKQ_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LLL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LLY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LMT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LNC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LNT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LOW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LRCX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LUK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LUV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\LYB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\L_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MAA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MAC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MAR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MAS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MAT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MCD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MCHP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MCK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MCO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MDLZ_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MDT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MET_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MGM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MHK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MKC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MLM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MMC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MMM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MNST_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MON_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MOS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MPC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MRK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MRO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MSFT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MSI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MTB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MTD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MU_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\MYL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\M_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NAVI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NBL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NCLH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NDAQ_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NEE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NEM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NFLX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NFX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NKE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NLSN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NOC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NOV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NRG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NSC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NTAP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NTRS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NUE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NVDA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NWL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NWSA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\NWS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\OKE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\OMC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ORCL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ORLY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\OXY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\O_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PAYX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PBCT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PCAR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PCG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PCLN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PDCO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PEG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PEP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PFE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PFG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PGR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PHM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PKG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PKI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PLD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PNC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PNR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PNW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PPG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PPL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PRGO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PRU_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PSA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PSX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PVH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PWR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PXD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\PYPL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\QCOM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\QRVO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RCL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\REGN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\REG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RF_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RHI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RHT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RJF_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RMD_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ROK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ROP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ROST_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RRC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RSG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\RTN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SBAC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SBUX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SCG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SCHW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SEE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SHW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SIG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SJM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SLB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SLG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SNA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SNI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SNPS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SPGI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SPG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SRCL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SRE_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\STI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\STT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\STX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\STZ_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SWKS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SWK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SYF_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SYK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SYMC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\SYY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TAP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TDG_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TEL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TGT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TIF_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TJX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TMK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TMO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TPR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TRIP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TROW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TRV_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TSCO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TSN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TSS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TWX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TXN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\TXT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\T_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UAA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UAL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UDR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UHS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ULTA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UNH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UNM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UNP_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UPS_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\URI_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\USB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\UTX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VAR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VFC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VIAB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VLO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VMC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VNO_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VRSK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VRSN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VRTX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VTR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\VZ_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\V_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WAT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WBA_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WDC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WEC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WFC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WHR_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WLTW_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WMB_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WMT_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WRK_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WU_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WYNN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WYN_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\WY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\XEC_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\XEL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\XLNX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\XL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\XOM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\XRAY_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\XRX_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\XYL_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\YUM_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ZBH_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ZION_data.csv',
 'C:\\DA_BA_material\\individual_stocks_5yr\\ZTS_data.csv']
In [4]:
len(glob.glob(r'C:\DA_BA_material\individual_stocks_5yr/*csv'))
Out[4]:
505
In [ ]:
In [5]:
company_list = [
    r'C:\\DA_BA_material\\individual_stocks_5yr\\AAPL_data.csv',
    r'C:\\DA_BA_material\\individual_stocks_5yr\\AMZN_data.csv',
    r'C:\\DA_BA_material\\individual_stocks_5yr\\GOOG_data.csv', 
    r'C:\\DA_BA_material\\individual_stocks_5yr\\MSFT_data.csv'
]
In [6]:
import warnings
from warnings import filterwarnings
filterwarnings('ignore')
In [7]:
all_data = pd.DataFrame()


for file in company_list:
    
    current_df = pd.read_csv(file)
    
    all_data = current_df.append(all_data , ignore_index=True)
    # full_df = pd.concat([full_df , current_df] , ignore_index=True)
In [8]:
all_data.shape
Out[8]:
(4752, 7)
In [9]:
all_data.head(6)
Out[9]:
date open high low close volume Name
0 2013-02-08 27.35 27.71 27.310 27.55 33318306 MSFT
1 2013-02-11 27.65 27.92 27.500 27.86 32247549 MSFT
2 2013-02-12 27.88 28.00 27.750 27.88 35990829 MSFT
3 2013-02-13 27.93 28.11 27.880 28.03 41715530 MSFT
4 2013-02-14 27.92 28.06 27.870 28.04 32663174 MSFT
5 2013-02-15 28.04 28.16 27.875 28.01 49650538 MSFT
In [10]:
all_data['Name'].unique()
Out[10]:
array(['MSFT', 'GOOG', 'AMZN', 'AAPL'], dtype=object)

Analysing change in price of the stock overtime¶

In [ ]:
In [ ]:
In [ ]:
In [11]:
all_data.isnull().sum()
Out[11]:
date      0
open      0
high      0
low       0
close     0
volume    0
Name      0
dtype: int64
In [12]:
all_data.dtypes
Out[12]:
date       object
open      float64
high      float64
low       float64
close     float64
volume      int64
Name       object
dtype: object
In [ ]:
In [13]:
all_data['date'] = pd.to_datetime(all_data['date'])
In [14]:
all_data['date']
Out[14]:
0      2013-02-08
1      2013-02-11
2      2013-02-12
3      2013-02-13
4      2013-02-14
          ...    
4747   2018-02-01
4748   2018-02-02
4749   2018-02-05
4750   2018-02-06
4751   2018-02-07
Name: date, Length: 4752, dtype: datetime64[ns]
In [ ]:
In [15]:
tech_list = all_data['Name'].unique()
In [16]:
tech_list
Out[16]:
array(['MSFT', 'GOOG', 'AMZN', 'AAPL'], dtype=object)
In [ ]:
In [17]:
plt.figure(figsize=(20,12))

for index , company in enumerate(tech_list , 1):
    plt.subplot(2 , 2 , index)
    filter1 = all_data['Name']==company
    df = all_data[filter1]
    plt.plot(df['date'] , df['close'])
    plt.title(company)

Analysing moving average of the various stocks¶

In [ ]:
In [ ]:
In [ ]:
In [18]:
all_data.head(15)
Out[18]:
date open high low close volume Name
0 2013-02-08 27.3500 27.71 27.310 27.550 33318306 MSFT
1 2013-02-11 27.6500 27.92 27.500 27.860 32247549 MSFT
2 2013-02-12 27.8800 28.00 27.750 27.880 35990829 MSFT
3 2013-02-13 27.9300 28.11 27.880 28.030 41715530 MSFT
4 2013-02-14 27.9200 28.06 27.870 28.040 32663174 MSFT
5 2013-02-15 28.0400 28.16 27.875 28.010 49650538 MSFT
6 2013-02-19 27.8801 28.09 27.800 28.045 38804616 MSFT
7 2013-02-20 28.1300 28.20 27.830 27.870 44109412 MSFT
8 2013-02-21 27.7400 27.74 27.230 27.490 49078338 MSFT
9 2013-02-22 27.6800 27.76 27.480 27.760 31425726 MSFT
10 2013-02-25 27.9700 28.05 27.370 27.370 48011248 MSFT
11 2013-02-26 27.3800 27.60 27.340 27.370 49917353 MSFT
12 2013-02-27 27.4200 28.00 27.330 27.810 36390889 MSFT
13 2013-02-28 27.8800 27.97 27.740 27.800 35836861 MSFT
14 2013-03-01 27.7200 27.98 27.520 27.950 34849287 MSFT
In [ ]:
In [19]:
all_data['close'].rolling(window=10).mean().head(14)
Out[19]:
0         NaN
1         NaN
2         NaN
3         NaN
4         NaN
5         NaN
6         NaN
7         NaN
8         NaN
9     27.8535
10    27.8355
11    27.7865
12    27.7795
13    27.7565
Name: close, dtype: float64
In [20]:
new_data = all_data.copy()
In [21]:
ma_day = [10 , 20 , 50]

for ma in ma_day:
    new_data['close'+str(ma)] = new_data['close'].rolling(ma).mean()
In [22]:
new_data.tail(7)
Out[22]:
date open high low close volume Name close10 close20 close50
4745 2018-01-30 165.525 167.3700 164.7000 166.97 46048185 AAPL 174.263 174.3340 172.9460
4746 2018-01-31 166.870 168.4417 166.5000 167.43 32478930 AAPL 173.096 174.0925 172.8726
4747 2018-02-01 167.165 168.6200 166.7600 167.78 47230787 AAPL 171.948 173.8700 172.8252
4748 2018-02-02 166.000 166.8000 160.1000 160.50 86593825 AAPL 170.152 173.2435 172.6356
4749 2018-02-05 159.100 163.8800 156.0000 156.49 72738522 AAPL 168.101 172.3180 172.3026
4750 2018-02-06 154.830 163.7200 154.0000 163.03 68243838 AAPL 166.700 171.7520 172.0640
4751 2018-02-07 163.085 163.4000 159.0685 159.54 51608580 AAPL 165.232 171.0125 171.7554
In [ ]:
In [23]:
new_data.set_index('date' , inplace=True)
In [24]:
new_data
Out[24]:
open high low close volume Name close10 close20 close50
date
2013-02-08 27.350 27.71 27.3100 27.55 33318306 MSFT NaN NaN NaN
2013-02-11 27.650 27.92 27.5000 27.86 32247549 MSFT NaN NaN NaN
2013-02-12 27.880 28.00 27.7500 27.88 35990829 MSFT NaN NaN NaN
2013-02-13 27.930 28.11 27.8800 28.03 41715530 MSFT NaN NaN NaN
2013-02-14 27.920 28.06 27.8700 28.04 32663174 MSFT NaN NaN NaN
... ... ... ... ... ... ... ... ... ...
2018-02-01 167.165 168.62 166.7600 167.78 47230787 AAPL 171.948 173.8700 172.8252
2018-02-02 166.000 166.80 160.1000 160.50 86593825 AAPL 170.152 173.2435 172.6356
2018-02-05 159.100 163.88 156.0000 156.49 72738522 AAPL 168.101 172.3180 172.3026
2018-02-06 154.830 163.72 154.0000 163.03 68243838 AAPL 166.700 171.7520 172.0640
2018-02-07 163.085 163.40 159.0685 159.54 51608580 AAPL 165.232 171.0125 171.7554

4752 rows × 9 columns

In [25]:
new_data.columns
Out[25]:
Index(['open', 'high', 'low', 'close', 'volume', 'Name', 'close10', 'close20',
       'close50'],
      dtype='object')
In [26]:
plt.figure(figsize=(20,16))

for index , company in enumerate(tech_list , 1):
    plt.subplot(2 , 2 , index)
    filter1 = new_data['Name']==company
    df = new_data[filter1]
    df[['close10', 'close20','close50']].plot(ax=plt.gca())
    plt.title(company)

Observing closing price change in Apple stock¶

In [ ]:
In [ ]:
In [27]:
company_list
Out[27]:
['C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\AAPL_data.csv',
 'C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\AMZN_data.csv',
 'C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\GOOG_data.csv',
 'C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\MSFT_data.csv']
In [28]:
apple = pd.read_csv(r'C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\AAPL_data.csv')
In [29]:
apple.head(4)
Out[29]:
date open high low close volume Name
0 2013-02-08 67.7142 68.4014 66.8928 67.8542 158168416 AAPL
1 2013-02-11 68.0714 69.2771 67.6071 68.5614 129029425 AAPL
2 2013-02-12 68.5014 68.9114 66.8205 66.8428 151829363 AAPL
3 2013-02-13 66.7442 67.6628 66.1742 66.7156 118721995 AAPL
In [30]:
apple['close']
Out[30]:
0        67.8542
1        68.5614
2        66.8428
3        66.7156
4        66.6556
          ...   
1254    167.7800
1255    160.5000
1256    156.4900
1257    163.0300
1258    159.5400
Name: close, Length: 1259, dtype: float64
In [31]:
apple.head(4)
Out[31]:
date open high low close volume Name
0 2013-02-08 67.7142 68.4014 66.8928 67.8542 158168416 AAPL
1 2013-02-11 68.0714 69.2771 67.6071 68.5614 129029425 AAPL
2 2013-02-12 68.5014 68.9114 66.8205 66.8428 151829363 AAPL
3 2013-02-13 66.7442 67.6628 66.1742 66.7156 118721995 AAPL
In [32]:
apple['Daily return(in %)'] = apple['close'].pct_change() * 100
In [33]:
apple.head(4)
Out[33]:
date open high low close volume Name Daily return(in %)
0 2013-02-08 67.7142 68.4014 66.8928 67.8542 158168416 AAPL NaN
1 2013-02-11 68.0714 69.2771 67.6071 68.5614 129029425 AAPL 1.042235
2 2013-02-12 68.5014 68.9114 66.8205 66.8428 151829363 AAPL -2.506658
3 2013-02-13 66.7442 67.6628 66.1742 66.7156 118721995 AAPL -0.190297
In [ ]:
In [34]:
import plotly.express as px
In [35]:
px.line(apple , x="date" , y="Daily return(in %)")

Resampling Analysis¶

In [36]:
apple.dtypes
Out[36]:
date                   object
open                  float64
high                  float64
low                   float64
close                 float64
volume                  int64
Name                   object
Daily return(in %)    float64
dtype: object
In [37]:
apple['date'] = pd.to_datetime(apple['date'])
In [38]:
apple.dtypes
Out[38]:
date                  datetime64[ns]
open                         float64
high                         float64
low                          float64
close                        float64
volume                         int64
Name                          object
Daily return(in %)           float64
dtype: object
In [39]:
apple.head(4)
Out[39]:
date open high low close volume Name Daily return(in %)
0 2013-02-08 67.7142 68.4014 66.8928 67.8542 158168416 AAPL NaN
1 2013-02-11 68.0714 69.2771 67.6071 68.5614 129029425 AAPL 1.042235
2 2013-02-12 68.5014 68.9114 66.8205 66.8428 151829363 AAPL -2.506658
3 2013-02-13 66.7442 67.6628 66.1742 66.7156 118721995 AAPL -0.190297
In [40]:
apple.set_index('date' , inplace=True)
In [41]:
apple.head(4)
Out[41]:
open high low close volume Name Daily return(in %)
date
2013-02-08 67.7142 68.4014 66.8928 67.8542 158168416 AAPL NaN
2013-02-11 68.0714 69.2771 67.6071 68.5614 129029425 AAPL 1.042235
2013-02-12 68.5014 68.9114 66.8205 66.8428 151829363 AAPL -2.506658
2013-02-13 66.7442 67.6628 66.1742 66.7156 118721995 AAPL -0.190297
In [42]:
apple['close'].resample('M').mean()
Out[42]:
date
2013-02-28     65.306264
2013-03-31     63.120110
2013-04-30     59.966432
2013-05-31     63.778927
2013-06-30     60.791120
                 ...    
2017-10-31    157.817273
2017-11-30    172.406190
2017-12-31    171.891500
2018-01-31    174.005238
2018-02-28    161.468000
Freq: M, Name: close, Length: 61, dtype: float64
In [43]:
apple['close'].resample('M').mean().plot()
Out[43]:
<Axes: xlabel='date'>
In [ ]:
In [44]:
apple['close'].resample('Y').mean()
Out[44]:
date
2013-12-31     67.237839
2014-12-31     92.264531
2015-12-31    120.039861
2016-12-31    104.604008
2017-12-31    150.585080
2018-12-31    171.594231
Freq: A-DEC, Name: close, dtype: float64
In [45]:
apple['close'].resample('Y').mean().plot()
Out[45]:
<Axes: xlabel='date'>
In [ ]:
In [46]:
apple['close'].resample('Q').mean()
Out[46]:
date
2013-03-31     64.020291
2013-06-30     61.534692
2013-09-30     66.320670
2013-12-31     75.567478
2014-03-31     76.086293
2014-06-30     85.117475
2014-09-30     98.163311
2014-12-31    108.821016
2015-03-31    120.776721
2015-06-30    127.937937
2015-09-30    117.303438
2015-12-31    114.299297
2016-03-31     99.655082
2016-06-30     99.401250
2016-09-30    105.866094
2016-12-31    113.399048
2017-03-31    131.712500
2017-06-30    147.875397
2017-09-30    155.304603
2017-12-31    167.148254
2018-03-31    171.594231
Freq: Q-DEC, Name: close, dtype: float64
In [47]:
apple['close'].resample('Q').mean().plot()
Out[47]:
<Axes: xlabel='date'>

Performing Multi-variate Analysis to understand co-relation¶

In [ ]:
In [48]:
company_list
Out[48]:
['C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\AAPL_data.csv',
 'C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\AMZN_data.csv',
 'C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\GOOG_data.csv',
 'C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\MSFT_data.csv']
In [49]:
company_list[0]
Out[49]:
'C:\\\\DA_BA_material\\\\individual_stocks_5yr\\\\AAPL_data.csv'
In [52]:
app = pd.read_csv(company_list[0])
amzn = pd.read_csv(company_list[1])
google = pd.read_csv(company_list[2])
msft = pd.read_csv(company_list[3])
In [53]:
closing_price = pd.DataFrame()
In [56]:
closing_price['apple_close'] = app['close']
closing_price['amzn_close'] = amzn['close']
closing_price['google_close'] = google['close']
closing_price['msft_close'] = msft['close']
In [57]:
closing_price
Out[57]:
apple_close amzn_close google_close msft_close
0 67.8542 261.95 558.46 27.55
1 68.5614 257.21 559.99 27.86
2 66.8428 258.70 556.97 27.88
3 66.7156 269.47 567.16 28.03
4 66.6556 269.24 567.00 28.04
... ... ... ... ...
1254 167.7800 1390.00 NaN 94.26
1255 160.5000 1429.95 NaN 91.78
1256 156.4900 1390.00 NaN 88.00
1257 163.0300 1442.84 NaN 91.33
1258 159.5400 1416.78 NaN 89.61

1259 rows × 4 columns

In [ ]:
In [58]:
sns.pairplot(closing_price)
Out[58]:
<seaborn.axisgrid.PairGrid at 0x21ab22d3590>
In [ ]:
In [ ]:
In [59]:
closing_price.corr()
Out[59]:
apple_close amzn_close google_close msft_close
apple_close 1.000000 0.819078 0.640522 0.899689
amzn_close 0.819078 1.000000 0.888456 0.955977
google_close 0.640522 0.888456 1.000000 0.907011
msft_close 0.899689 0.955977 0.907011 1.000000
In [61]:
sns.heatmap(closing_price.corr() , annot=True)
Out[61]:
<Axes: >

Performing Co-relation Analysis¶

In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [62]:
closing_price
Out[62]:
apple_close amzn_close google_close msft_close
0 67.8542 261.95 558.46 27.55
1 68.5614 257.21 559.99 27.86
2 66.8428 258.70 556.97 27.88
3 66.7156 269.47 567.16 28.03
4 66.6556 269.24 567.00 28.04
... ... ... ... ...
1254 167.7800 1390.00 NaN 94.26
1255 160.5000 1429.95 NaN 91.78
1256 156.4900 1390.00 NaN 88.00
1257 163.0300 1442.84 NaN 91.33
1258 159.5400 1416.78 NaN 89.61

1259 rows × 4 columns

In [63]:
closing_price['apple_close']
Out[63]:
0        67.8542
1        68.5614
2        66.8428
3        66.7156
4        66.6556
          ...   
1254    167.7800
1255    160.5000
1256    156.4900
1257    163.0300
1258    159.5400
Name: apple_close, Length: 1259, dtype: float64
In [64]:
closing_price['apple_close'].shift(1)
Out[64]:
0            NaN
1        67.8542
2        68.5614
3        66.8428
4        66.7156
          ...   
1254    167.4300
1255    167.7800
1256    160.5000
1257    156.4900
1258    163.0300
Name: apple_close, Length: 1259, dtype: float64
In [67]:
(closing_price['apple_close'] - closing_price['apple_close'].shift(1))/closing_price['apple_close'].shift(1) * 100
Out[67]:
0            NaN
1       1.042235
2      -2.506658
3      -0.190297
4      -0.089934
          ...   
1254    0.209043
1255   -4.339015
1256   -2.498442
1257    4.179181
1258   -2.140710
Name: apple_close, Length: 1259, dtype: float64
In [ ]:
In [74]:
for col in closing_price.columns:
    closing_price[col + '_pct_change'] = (closing_price[col] - closing_price[col].shift(1))/closing_price[col].shift(1) * 100
In [75]:
closing_price
Out[75]:
apple_close amzn_close google_close msft_close apple_close_pct_change amzn_close_pct_change google_close_pct_change msft_close_pct_change
0 67.8542 261.95 558.46 27.55 NaN NaN NaN NaN
1 68.5614 257.21 559.99 27.86 1.042235 -1.809506 0.273968 1.125227
2 66.8428 258.70 556.97 27.88 -2.506658 0.579293 -0.539295 0.071788
3 66.7156 269.47 567.16 28.03 -0.190297 4.163123 1.829542 0.538020
4 66.6556 269.24 567.00 28.04 -0.089934 -0.085353 -0.028211 0.035676
... ... ... ... ... ... ... ... ...
1254 167.7800 1390.00 NaN 94.26 0.209043 -4.196734 NaN -0.789391
1255 160.5000 1429.95 NaN 91.78 -4.339015 2.874101 NaN -2.631021
1256 156.4900 1390.00 NaN 88.00 -2.498442 -2.793804 NaN -4.118544
1257 163.0300 1442.84 NaN 91.33 4.179181 3.801439 NaN 3.784091
1258 159.5400 1416.78 NaN 89.61 -2.140710 -1.806160 NaN -1.883280

1259 rows × 8 columns

In [76]:
closing_price.columns
Out[76]:
Index(['apple_close', 'amzn_close', 'google_close', 'msft_close',
       'apple_close_pct_change', 'amzn_close_pct_change',
       'google_close_pct_change', 'msft_close_pct_change'],
      dtype='object')
In [78]:
clsing_p = closing_price[['apple_close_pct_change', 'amzn_close_pct_change',
       'google_close_pct_change', 'msft_close_pct_change']]
In [79]:
clsing_p
Out[79]:
apple_close_pct_change amzn_close_pct_change google_close_pct_change msft_close_pct_change
0 NaN NaN NaN NaN
1 1.042235 -1.809506 0.273968 1.125227
2 -2.506658 0.579293 -0.539295 0.071788
3 -0.190297 4.163123 1.829542 0.538020
4 -0.089934 -0.085353 -0.028211 0.035676
... ... ... ... ...
1254 0.209043 -4.196734 NaN -0.789391
1255 -4.339015 2.874101 NaN -2.631021
1256 -2.498442 -2.793804 NaN -4.118544
1257 4.179181 3.801439 NaN 3.784091
1258 -2.140710 -1.806160 NaN -1.883280

1259 rows × 4 columns

In [ ]:
In [81]:
g = sns.PairGrid(data = clsing_p)
g.map_diag(sns.histplot)
g.map_lower(sns.scatterplot)
g.map_upper(sns.kdeplot)
Out[81]:
<seaborn.axisgrid.PairGrid at 0x21ab7a61510>
In [ ]:
In [82]:
clsing_p.corr()
Out[82]:
apple_close_pct_change amzn_close_pct_change google_close_pct_change msft_close_pct_change
apple_close_pct_change 1.000000 0.287659 0.036202 0.366598
amzn_close_pct_change 0.287659 1.000000 0.027698 0.402678
google_close_pct_change 0.036202 0.027698 1.000000 0.038939
msft_close_pct_change 0.366598 0.402678 0.038939 1.000000

40% probability that whenever amzn stock decreases, msft stock will also decrease¶

In [ ]:
In [ ]:
In [ ]: